pandas Experts in Düsseldorf

• Led end-to-end delivery of ML/AI applications for the QuantistryLab simulation platform, from requirements definition and solution design to development, testing, deployment, and production support, coordinating efforts across back-end, DevOps, and ML teams
• Designed and implemented a compound search system with an open-weights LLM, the Pydantic AI agent framework, and the Model Context Protocol (MCP), exposing it through FastAPI endpoints
• Deployed and configured vLLM-based LLM serving on Kubernetes
• Built CI/CD pipelines and Helm charts to automate deployments across staging and production environments
• Instrumented the search system with OpenTelemetry spans and traces, integrating with the Honeycomb observability platform to monitor component-level latency and functional errors
• Developed a custom evaluation dataset and implemented evaluations for retrieval relevance, answer correctness, tool-call accuracy, and end-to-end task success
• Reduced infrared spectrum prediction time by 83% (from 60 to 10 minutes) by replacing a quantum-mechanical model with a pretrained graph neural network; fine-tuned the model using PyTorch, built and containerized the inference pipeline with Docker, and integrated it into the platform
• Implemented an MLflow model registry with MinIO-backed artifact storage
• Advised sales and science teams on ML/AI applications for prospective client projects, providing technical expertise to shape proposed solutions and prototypes

Technologies: AWS, Hetzner, Kubernetes, Helm, Docker, vLLM, Pydantic AI, MCP, Qwen, Llama 3, MLflow, MinIO, GitHub Actions, Python, FastAPI, OpenTelemetry, Honeycomb, PyTorch, Polars, pytest

• Title: Enhancing Syntactic Awareness in Transformer Language Models for Hindi Dependency Parsing
• Investigated syntactic knowledge captured by transformer language models (RoBERTa, XLM-RoBERTa) for Hindi dependency parsing, a morphologically rich and low-resource language.
• Developed structure-aware model variants (Struct_Roberta_hi, Struct_XLMR) by integrating a CNN-based parser network between transformer layers, inspired by the StructFormer architecture.
• Conducted extensive error analysis including label-wise, distance-based, direction-based, sentence length-based, and LVC/Non-LVC evaluations.
• Evaluated models on downstream NLP tasks (NER, POS tagging) using the IndicXTREME benchmark.

• Gathered and analyzed requirements in close collaboration with business departments to develop data-driven solutions and scalable PowerBI reporting infrastructures.
• Conducted detailed error analyses and optimized existing semantic and data models to ensure a robust data architecture and high data quality and to improve PowerBI reporting.
• Developed and implemented scalable ETL processes for data preparation and integration.
• Built a wiki for table and view descriptions as well as PowerBI PowerQuery and KPI documentation to ensure a consistent understanding of data structures and key performance indicators.

• Architecting and developing SaaS platform for graphical definition and execution of pandas data processing pipelines
• Developed POlyglott, an open-source Python CLI tool for translation workflow management featuring PO file parsing, quality linting with glossary enforcement, and DeepL API integration for machine translation
• Developed web application for material compliance management (EU REACH) using Django and modern web technologies
• Built automated infrastructure platform using Proxmox, Terraform, and Ansible — VM provisioning, configuration management, internal DNS, and fleet-wide security hardening across multiple subnets

• Led large-scale data analysis on high-volume event data, applying statistical modeling and time-series methods to detect weak signals in noisy environments
• Designed and maintained scalable Python data pipelines for real and simulated datasets, optimizing signal detection and background estimation at scale
• Applied advanced statistical inference techniques (likelihood-based modeling, hypothesis testing) to support quantitative decision-making
• Deployed data-processing workflows on HPC clusters using Slurm, enabling parallelized analysis and large-scale batch execution
• Built reproducible, version-controlled data workflows using Python, Bash, and Git to ensure reliability and traceability of results
• Translated complex experimental data into actionable insights, enabling quantitative decision-making

Implemented Power BI reporting for various departments at an energy provider. Agile project: responsible for organizing and coordinating with departments and IT, and regularly presented interim steps and results to project management.

• Managed the entire hiring process with a focus on data-driven decision-making.
• Analyzed recruiting data using Excel and ATS to optimize processes effectively.

• AI assistant using an offline model, capable of voice recognition and real time Text-to-Speech.